Aspects of the present disclosure include systems, methods, and devices to provide estimations of vehicular pick-up/drop-off zone (PDZ) availability. A request for vehicular PDZ availability at a location is received from a vehicular autonomy system of a vehicle. The request specifies an estimated time of arrival at the location. The PDZ availability at the location at the estimated time of arrival is estimated using a probabilistic model. A response to the request is generated based on the estimated PDZ availability. The response indicates the estimated PDZ availability. The response is transmitted to the vehicular autonomy system responsive to the request.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A system comprising: at least one processor of a machine; and a memory storing instructions that cause the at least one processor to perform operations comprising: receiving, from a vehicular autonomy system of a vehicle, a request for vehicular pick-up/drop off (PDZ) availability at a location, the request specifying an estimated time of arrival at the location; estimating, using a probabilistic model, the PDZ availability at the location at the estimated time of arrival, the probabilistic model comprising a machine learning model that is trained based on historical training data to extract one or more features from the historical training data and compute a probabilistic estimation of a given PDZ being free or occupied based on the one or more features extracted from the historical training data; generating a response to the request based on the estimated PDZ availability; transmitting, to the vehicular autonomy system, the response to the request, the response indicating the estimated PDZ availability; and causing the vehicle to navigate to the PDZ at the location according a route.
The system addresses the challenge of efficiently managing vehicular pick-up and drop-off zones (PDZs) for autonomous vehicles by predicting PDZ availability at a given location and time. The system includes at least one processor and a memory storing instructions that, when executed, enable the processor to receive a request from a vehicular autonomy system for PDZ availability at a specified location, including an estimated time of arrival. A probabilistic model, trained on historical data using machine learning, estimates the likelihood of the PDZ being free or occupied at the estimated time. The model extracts relevant features from the historical data to compute this probabilistic estimation. The system generates a response indicating the estimated PDZ availability and transmits it to the vehicular autonomy system. Based on this response, the vehicle navigates to the PDZ according to a determined route. The probabilistic model leverages historical training data to improve accuracy in predicting PDZ availability, ensuring smoother and more efficient vehicle operations. This approach optimizes the use of limited PDZ resources by reducing wait times and improving route planning for autonomous vehicles.
2. The system of claim 1 , wherein the historical training data comprises global position system data from one or more vehicles, wherein the estimating of the PDZ availability at the location comprises: identifying a set of PDZs associated with the location; and determining, using the probabilistic model, an estimated availability of the set of PDZs at the estimated time of arrival.
This system relates to estimating the availability of parking drop zones (PDZs) for vehicles using historical GPS data and probabilistic modeling. The problem addressed is the lack of real-time information about parking availability, which leads to inefficiencies in vehicle routing and parking management. The system leverages historical GPS data from multiple vehicles to train a probabilistic model that predicts PDZ availability at a specific location and time. The historical data includes GPS coordinates, timestamps, and vehicle identifiers, which are used to identify patterns in parking usage. The system first identifies a set of PDZs associated with a given location, then applies the probabilistic model to estimate the availability of these PDZs at the estimated time of arrival of a vehicle. The model considers factors such as time of day, day of the week, and historical occupancy trends to provide an availability prediction. This enables vehicles to plan routes more efficiently, reducing time spent searching for parking. The system may also integrate with navigation systems to provide dynamic routing suggestions based on predicted PDZ availability.
3. The system of claim 2 , wherein the determining the estimated availability of the set of PDZs at the estimated time of arrival comprises: determining, using the probabilistic model, an individual estimated availability of each PDZ in the set of PDZs; and determining the estimated availability of the set of PDZs based on the individual estimated availability of each PDZ in the set of PDZs.
The invention relates to a system for managing parking availability predictions, particularly for parking demand zones (PDZs). The system addresses the challenge of accurately estimating parking availability at future times to assist drivers in finding parking spaces efficiently. The system uses a probabilistic model to predict the likelihood of parking availability in specific PDZs at an estimated time of arrival. For a given set of PDZs, the system first calculates the individual estimated availability of each PDZ using the probabilistic model. It then aggregates these individual estimates to determine the overall availability of the entire set of PDZs. This approach allows the system to provide drivers with reliable parking availability information, helping them make informed decisions about where and when to park. The probabilistic model accounts for historical data, real-time occupancy, and other factors to improve prediction accuracy. The system may also integrate with navigation or parking guidance applications to enhance user experience.
4. The system of claim 2 , wherein the generating of the response comprises: selecting a target PDZ from the set of PDZs based in part on the estimated availability of the target PDZ in the set of PDZs, wherein the response indicates the target PDZ.
The invention relates to a system for managing and allocating parking domains (PDZs) in a transportation network. The system addresses the challenge of efficiently directing users to available parking domains while optimizing resource utilization and minimizing congestion. The system generates responses to user requests by selecting a target parking domain from a set of available PDZs based on factors including the estimated availability of each PDZ. The response provided to the user indicates the selected target PDZ, guiding them to an optimal parking location. The system may also include a user interface for receiving user requests and a processing module that evaluates PDZ availability data to determine the most suitable PDZ for allocation. The selection process considers real-time or near-real-time availability metrics to ensure accurate and efficient parking domain assignment. This approach enhances user experience by reducing search time and improving parking efficiency in urban or high-traffic areas. The system may further integrate with navigation services to provide seamless guidance to the selected PDZ.
5. The system of claim 4 , wherein the selecting of the target PDZ is further based on a proximity of the target PDZ to at least one other PDZ.
This invention relates to a system for selecting target protein domains, specifically PDZ domains, in a protein interaction network. The system addresses the challenge of efficiently identifying and prioritizing PDZ domains for further analysis or therapeutic targeting by considering their spatial relationships within the network. The system includes a computational model that evaluates the proximity of a target PDZ domain to at least one other PDZ domain, in addition to other selection criteria. By incorporating proximity as a factor, the system improves the accuracy and relevance of target selection, ensuring that closely interacting PDZ domains are considered together. This approach enhances the understanding of protein interactions and facilitates the development of targeted interventions. The system may be used in drug discovery, protein engineering, or structural biology to optimize the identification of key protein domains for experimental or clinical applications. The proximity-based selection criterion helps avoid isolated or less relevant PDZ domains, focusing instead on those with significant spatial or functional relationships.
6. The system of claim 4 , wherein the generating of the response further comprises: generating a set of instructions that, when received by the vehicular autonomy system, cause the vehicle autonomy system to control operation of a vehicle such that the vehicle navigates to the target PDZ.
This invention relates to autonomous vehicle navigation systems designed to improve the efficiency and accuracy of vehicle routing to designated parking zones (PDZs). The system addresses the challenge of dynamically guiding autonomous vehicles to optimal parking locations based on real-time data, ensuring efficient use of parking infrastructure and minimizing travel time. The system generates a response to a navigation request by producing a set of instructions that direct the vehicle autonomy system to control the vehicle's operation. These instructions enable the vehicle to navigate autonomously to a specified target PDZ. The system integrates real-time data, such as traffic conditions, parking availability, and route optimization algorithms, to determine the most efficient path to the PDZ. The instructions may include steering, acceleration, braking, and route selection commands, ensuring the vehicle adheres to traffic laws and safety protocols while reaching the destination. Additionally, the system may incorporate predictive analytics to anticipate parking availability and adjust navigation accordingly. The instructions are transmitted to the vehicle's autonomy system, which executes them to control the vehicle's movement, ensuring seamless and accurate navigation to the target PDZ. This approach enhances parking efficiency, reduces congestion, and improves overall traffic flow in urban environments.
7. The system of claim 4 , wherein the generating of the response further comprises: generating a route for the vehicle to the target PDZ based on a current location and target location of the vehicle.
This invention relates to a vehicle navigation system designed to guide a vehicle to a designated parking zone (PDZ). The system addresses the challenge of efficiently directing vehicles to available parking spaces, reducing time spent searching for parking and minimizing traffic congestion. The system determines a vehicle's current location and the target PDZ location, then generates an optimized route to the PDZ. This routing process considers real-time traffic conditions, road restrictions, and other dynamic factors to ensure the most efficient path. The system may also integrate with external data sources, such as parking availability sensors or traffic management systems, to refine route calculations. Additionally, the system can provide turn-by-turn navigation instructions to the driver, ensuring precise guidance to the PDZ. The routing functionality is part of a broader system that may include features like PDZ identification, reservation management, and payment processing, all aimed at streamlining the parking experience. The invention is particularly useful in urban environments where parking availability is limited and efficient navigation is critical.
8. The system of claim 1 , wherein the operations further comprise: obtaining data comprising one or more indicia of PDZ availability at the location; wherein the estimating of the PDZ availability at the location at the estimated time of arrival is further based on the one or more indicia of PDZ availability at the location.
A system for managing parking availability in a designated parking zone (PDZ) estimates PDZ availability at a specific location and time. The system collects real-time data on parking space occupancy, traffic conditions, and other factors influencing parking availability. This data is used to predict whether a parking space will be available at a user's estimated time of arrival. The system also obtains additional data, such as historical parking patterns, event schedules, or local regulations, to refine its estimates. By integrating these indicators of PDZ availability, the system provides more accurate predictions, helping users plan their parking needs efficiently. The system may also include features for dynamic updates, user notifications, and integration with navigation tools to guide users to available parking spaces. The goal is to reduce parking-related delays and improve urban mobility by leveraging real-time and predictive analytics.
9. The system of claim 8 , wherein: the vehicular autonomy system is a first vehicular autonomy system of a first vehicle; the obtaining of the data comprises: transmitting a request to a second vehicular autonomy system of a second vehicle that causes the second vehicle to travel to the location; and detecting an indication of the PDZ availability at the location when the second vehicle is near the location.
This invention relates to vehicular autonomy systems designed to manage parking and delivery zones (PDZs) in urban environments. The problem addressed is the inefficiency and uncertainty in determining the availability of PDZs, which are designated areas for parking or delivering goods. Traditional methods rely on static data or manual reporting, leading to outdated or inaccurate information. The system includes a vehicular autonomy system in a first vehicle that obtains data about PDZ availability. To do this, the system transmits a request to a second vehicular autonomy system in a second vehicle, instructing it to travel to the location of the PDZ. As the second vehicle approaches the location, the system detects an indication of PDZ availability, such as whether the zone is occupied or free. This dynamic approach ensures real-time verification of PDZ status, improving efficiency for autonomous vehicles and delivery services. The system may also include a communication interface to transmit the PDZ availability data to other vehicles or infrastructure, enabling coordinated use of PDZs. The second vehicle may be equipped with sensors or cameras to confirm the PDZ status visually or through other detection methods. This method reduces the need for human intervention and enhances the reliability of PDZ management in autonomous vehicle operations.
10. The system of claim 9 , wherein: the obtaining of the data further comprises: causing display, on a display device inside the second vehicle, of a prompt for an occupant of the second vehicle to provide an indication of the PDZ availability at the location; and receiving a response to the prompt comprising the indication of the PDZ availability specified by the occupant of the second vehicle.
This invention relates to a system for determining the availability of a parking space within a Parking Demand Zone (PDZ) using data obtained from vehicles. The system addresses the challenge of efficiently identifying available parking spaces in urban areas where parking demand is high, by leveraging real-time input from vehicle occupants. The system includes a first vehicle equipped with a processor and a communication interface, and a second vehicle also equipped with a processor and a communication interface. The first vehicle obtains data related to PDZ availability at a specific location by prompting an occupant of the second vehicle to provide an indication of whether a parking space is available. The prompt is displayed on a display device inside the second vehicle, and the system receives the occupant's response, which specifies the PDZ availability. This data is then used to update parking availability information, helping drivers locate open spaces more efficiently. The system may also include additional features such as transmitting the obtained data to a remote server or other vehicles to enhance the accuracy and coverage of parking availability information. The invention improves urban mobility by reducing the time and effort required to find parking, thereby decreasing traffic congestion and emissions.
11. The system of claim 8 , wherein: the vehicular autonomy system is a first vehicular autonomy system of a first vehicle; the obtaining of the data comprises accessing sensor data generated by one or more sensors of a second vehicular autonomy system of a second vehicle.
This invention relates to vehicular autonomy systems that enhance situational awareness by integrating sensor data from multiple vehicles. The problem addressed is the limited perception range and environmental understanding of individual autonomous vehicles, which can lead to safety risks or operational inefficiencies. The solution involves a system where a first vehicle's autonomy system accesses and utilizes sensor data from a second vehicle's autonomy system. This shared data may include real-time information about road conditions, obstacles, traffic patterns, or other environmental factors that the first vehicle's own sensors may not detect. By leveraging external sensor inputs, the first vehicle's autonomy system can make more informed decisions, improving navigation, collision avoidance, and overall driving performance. The system may also include features such as data fusion, where sensor inputs from multiple sources are combined to create a more comprehensive environmental model. This approach enhances the reliability and accuracy of autonomous driving systems, particularly in complex or dynamic environments. The invention is applicable to various autonomous vehicle configurations, including fully autonomous and semi-autonomous systems.
12. The system of claim 8 , further comprising: updating the probabilistic model based on the more indicia of PDZ availability at the location.
A system for managing parking availability uses a probabilistic model to predict parking space availability at a specific location. The system collects real-time data on parking demand and availability, including historical usage patterns, sensor data from parking spaces, and user-reported information. The probabilistic model processes this data to generate predictions about the likelihood of finding available parking at the location. The system then provides these predictions to users, helping them make informed decisions about where and when to park. Additionally, the system continuously updates the probabilistic model by incorporating new data on parking demand and availability, ensuring the predictions remain accurate over time. This dynamic updating process allows the system to adapt to changing conditions, such as seasonal variations, special events, or infrastructure changes. The system may also integrate with navigation tools to guide users to the most likely available parking spots, reducing congestion and improving efficiency in urban areas. The probabilistic model may use machine learning techniques to refine its predictions based on the collected data, enhancing accuracy and reliability.
13. The system of claim 1 , further comprising: wherein the probabilistic model is trained based on the historical training data that comprises one or more of: user-generated information; vehicle driving logs; vehicular sensor logs; traffic information; public transit schedules; parking restrictions; global position system data from one or more vehicles; and parking spot occupancy data obtained from parking sensors.
This invention relates to a system for optimizing vehicle navigation and parking assistance using a probabilistic model trained on diverse data sources. The system addresses the challenge of efficiently guiding drivers to available parking spots while minimizing travel time and fuel consumption. The probabilistic model leverages historical training data, including user-generated information, vehicle driving logs, vehicular sensor logs, traffic information, public transit schedules, parking restrictions, GPS data from multiple vehicles, and real-time parking spot occupancy data from parking sensors. By analyzing this comprehensive dataset, the model predicts parking availability, optimal routes, and potential parking violations, enhancing navigation accuracy and user experience. The system integrates these data sources to provide dynamic, data-driven recommendations, improving urban mobility and reducing congestion. The probabilistic model continuously updates based on new data, ensuring adaptive and reliable performance in varying conditions. This approach combines real-time and historical data to offer a robust solution for smart parking and navigation assistance.
14. A computer-implemented method comprising: receiving, from a vehicular autonomy system of a vehicle, a request for vehicular pick-up/drop off (PDZ) availability at a location, the request specifying an estimated time of arrival at the location; estimating, using a probabilistic model, the PDZ availability at the location at the estimated time of arrival, the probabilistic model comprising a machine learning model that is trained based on historical training data to extract one or more features from the historical training data and compute a probabilistic estimation of a given PDZ being free or occupied based on the one or more features extracted from the historical training data; generating, using one or more processors of a machine, a response to the request based on the estimated PDZ availability; transmitting, to the vehicular autonomy system, the response to the request, the response indicating the estimated PDZ availability; and causing the vehicle to navigate to the PDZ at the location according a route.
This invention relates to a computer-implemented method for predicting and managing vehicular pick-up/drop-off (PDZ) availability in autonomous vehicle systems. The method addresses the challenge of ensuring autonomous vehicles can efficiently locate and access available PDZs at a given location, particularly when navigating to a destination. The method involves receiving a request from a vehicular autonomy system, specifying an estimated time of arrival at a target location. A probabilistic model, trained using historical data, analyzes the request to estimate PDZ availability at the specified time. The model extracts relevant features from the historical data, such as past occupancy patterns, time-based trends, and environmental factors, to compute a probabilistic assessment of whether a PDZ will be free or occupied. Based on this estimation, a response is generated and transmitted back to the autonomy system, indicating the likelihood of PDZ availability. The autonomy system then uses this information to navigate the vehicle to the PDZ according to an optimized route. The method improves efficiency by reducing uncertainty in PDZ availability, minimizing idle time, and enhancing the overall reliability of autonomous vehicle operations. The probabilistic approach allows for dynamic adjustments based on real-world conditions, ensuring better resource utilization and passenger experience.
15. The computer-implemented method of claim 14 , wherein the estimating of the PDZ availability at the location comprises: identifying a set of PDZs associated with the location; and determining, using the probabilistic model, an individual estimated availability of each PDZ in the set of PDZs; and determining the estimated availability of the set of PDZs based on the individual estimated availability of each PDZ in the set of PDZs.
This invention relates to estimating the availability of parking spaces in a designated parking zone (PDZ) using a probabilistic model. The problem addressed is the lack of real-time or accurate information about parking space availability, which leads to inefficiencies in parking management and user experience. The method involves analyzing a location to determine the availability of parking spaces within one or more PDZs associated with that location. First, a set of PDZs linked to the location is identified. Then, a probabilistic model is used to calculate the individual estimated availability of each PDZ in the set. The overall estimated availability for the entire set of PDZs is derived from these individual estimates. The probabilistic model may incorporate historical data, real-time sensor inputs, or other relevant factors to predict availability with higher accuracy. This approach helps users and parking management systems make informed decisions about parking, reducing search times and improving resource utilization. The method can be applied in urban areas, commercial zones, or any location where parking availability is a concern.
16. The computer-implemented method of claim 15 , wherein the generating of the response comprises: selecting a target PDZ from the set of PDZs based in part on the individual estimated availability of the target PDZ, wherein the response indicates the target PDZ.
This invention relates to a computer-implemented method for managing and selecting target PDZs (Potential Delivery Zones) in a delivery or logistics system. The method addresses the challenge of efficiently allocating resources by dynamically selecting the most suitable PDZ based on real-time availability data. The system first identifies a set of PDZs relevant to a given request, then estimates the availability of each PDZ by analyzing factors such as current workload, capacity, and operational constraints. The method then generates a response that includes the selected target PDZ, which is chosen based on its estimated availability among other criteria. This ensures optimal resource utilization and minimizes delays in delivery or service fulfillment. The selection process may also incorporate additional parameters, such as proximity, cost, or priority, to further refine the choice of the target PDZ. The invention improves efficiency in logistics operations by dynamically adapting to changing conditions and ensuring that the most appropriate PDZ is selected for each request.
17. The computer-implemented method of claim 16 , wherein the generating of the response further comprises: generating a route for the vehicle to the target PDZ based on a current location and target location of the vehicle; and generating a set of instructions that, when received by the vehicular autonomy system, cause the vehicle autonomy system to control operation of a vehicle such that the vehicle travels to along the route to the target PDZ.
This invention relates to autonomous vehicle navigation systems designed to guide vehicles to designated parking drop zones (PDZs). The problem addressed is the need for precise, automated routing of autonomous vehicles to specific parking locations, ensuring efficient and accurate navigation without manual intervention. The method involves generating a response that includes a route from the vehicle's current location to a target PDZ. The route is calculated based on the vehicle's current position and the target PDZ's location. Additionally, the method generates a set of instructions that, when processed by the vehicle's autonomy system, direct the vehicle to follow the calculated route to the target PDZ. These instructions enable the autonomy system to control the vehicle's operation, including steering, acceleration, and braking, to ensure the vehicle travels along the intended path. The system ensures that the vehicle navigates accurately to the designated parking area, improving efficiency and reducing the need for human oversight. The method may also integrate with broader autonomous vehicle control systems to enhance overall navigation capabilities.
18. The computer-implemented method of claim 14 , further comprising: obtaining data comprising one or more indicia of PDZ availability at the location; and updating the probabilistic model based on the more indicia of PDZ availability at the location; wherein the estimating of the PDZ availability at the location at the estimated time of arrival is further based on the one or more indicia of PDZ availability at the location.
This invention relates to a computer-implemented method for estimating parking availability in a parking demand zone (PDZ) at a specific location and time. The method addresses the challenge of accurately predicting parking availability to reduce driver frustration and improve urban traffic flow. The system collects real-time and historical data on parking occupancy, traffic patterns, and other relevant factors to generate a probabilistic model that estimates parking availability at a given location and estimated time of arrival (ETA). The model is dynamically updated based on new data inputs, including real-time parking occupancy, traffic conditions, and other environmental factors. Additionally, the method incorporates one or more indicia of PDZ availability, such as sensor data, user-reported availability, or municipal parking regulations, to refine the probabilistic model. By continuously updating the model with these indicators, the system provides more accurate and reliable predictions of parking availability, helping drivers make informed decisions and reducing unnecessary traffic congestion caused by drivers searching for parking. The method is particularly useful in urban areas where parking demand is high and real-time availability data is critical for efficient navigation.
19. The computer-implemented method of claim 18 , wherein: the vehicular autonomy system is a first vehicular autonomy system of a first vehicle; the obtaining of the data comprises: transmitting a request to a second vehicular autonomy system of a second vehicle that causes the second vehicle to travel to the location; and detecting an indication of the PDZ availability at the location when the second vehicle is near the location.
This invention relates to vehicular autonomy systems and the management of parking detection zones (PDZs). The problem addressed is the need for autonomous vehicles to efficiently determine the availability of parking spaces in real-time, particularly in dynamic urban environments where parking conditions change frequently. The method involves a first autonomous vehicle obtaining data about PDZ availability at a specific location. To do this, the first vehicle transmits a request to a second autonomous vehicle, instructing it to travel to the target location. As the second vehicle approaches the location, it detects and reports an indication of PDZ availability, such as whether a parking spot is occupied or vacant. This approach leverages multiple autonomous vehicles to gather and share real-time parking data, improving the accuracy and reliability of parking availability information for the first vehicle. The system ensures that parking data is up-to-date by using active verification through another vehicle rather than relying solely on static databases or sensors. This method enhances the efficiency of autonomous vehicle navigation by reducing the time spent searching for parking and minimizing unnecessary travel. The solution is particularly useful in high-demand parking areas where traditional detection methods may be unreliable or outdated.
20. A tangible computer-readable medium storing instructions that, when executed by one or more processors of a machine, cause the one or more processors of the machine to perform operations comprising: receiving, from a vehicular autonomy system of a vehicle, a request for vehicular pick-up/drop off (PDZ) availability at a location, the request specifying an estimated time of arrival at the location; estimating, using a probabilistic model, the PDZ availability at the location at the estimated time of arrival, the probabilistic model comprising a machine learning model that is trained based on historical training data to extract one or more features from the historical training data and compute a probabilistic estimation of a given PDZ being free or occupied based on the one or more features extracted from the historical training data; generating a response to the request based on the estimated PDZ availability; transmitting, to the vehicular autonomy system, the response to the request, the response indicating the estimated PDZ availability; and causing the vehicle to navigate to the PDZ at the location according a route.
This invention relates to autonomous vehicle navigation systems, specifically addressing the challenge of predicting parking or pick-up/drop-off (PDZ) space availability at a given location and time. The system receives a request from a vehicle's autonomy system, including an estimated time of arrival, and uses a probabilistic model to assess PDZ availability. The probabilistic model is a machine learning system trained on historical data to identify relevant features (e.g., time of day, location characteristics, event schedules) and compute the likelihood of a PDZ being free or occupied at the specified time. The system generates a response indicating the estimated availability and transmits it to the vehicle's autonomy system. If the PDZ is available, the vehicle navigates to the location according to a determined route. The machine learning model continuously improves by learning from historical data, enabling more accurate predictions over time. This approach optimizes autonomous vehicle routing by reducing uncertainty around parking or pick-up/drop-off space availability, improving efficiency and reducing idle time.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
July 17, 2019
April 12, 2022
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.